Model-Driven Graph Contrastive Learning

TL;DR

MGCL introduces a graph contrastive learning framework that uses graphons to guide data-adaptive augmentations, improving representation learning by leveraging the underlying generative process of graphs.

Contribution

This work is the first to incorporate graphon-based generative models into contrastive learning, enabling principled and data-driven augmentations for graph representations.

Findings

Achieves state-of-the-art results on benchmark datasets.

Outperforms existing GCL methods with heuristic augmentations.

Effectively captures shared semantics through graphon-informed clustering.

Abstract

We propose $\textbf{MGCL}$, a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive learning by accounting for the data's underlying generative process. GCL has emerged as a powerful self-supervised framework for learning expressive node or graph representations without relying on annotated labels, which are often scarce in real-world data. By contrasting augmented views of graph data, GCL has demonstrated strong performance across various downstream tasks, such as node and graph classification. However, existing methods typically rely on manually designed or heuristic augmentation strategies that are not tailored to the underlying data distribution and operate at the individual graph level, ignoring similarities among graphs generated from the same model. Conversely, in our proposed approach, MGCL first estimates the graphon associated with the observed data and then defines a graphon-informed augmentation process, enabling data-adaptive and principled augmentations. Additionally, for graph-level tasks, MGCL clusters the dataset and estimates a graphon per group, enabling contrastive pairs to reflect shared semantics and structure. Extensive experiments on benchmark datasets demonstrate that MGCL achieves state-of-the-art performance, highlighting the advantages of incorporating generative models into GCL.